AI Paper Atlas

Research map / 3D vision / Human pose estimation

TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction

Ao Li, Yonggen Ling, Yiyang Lin, Yuji Wang, Yong Deng, Yansong Tang

ECCV 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add camera intrinsics unification (fixed focal length) (ablation)TAIHRI · Harmony4D-Egocentric (Upper)G-MPJPE (mm): 425.13 -> 93.83Improved
add camera intrinsics unification (fixed focal length) (ablation)TAIHRI · Harmony4D-Egocentric (Lower)G-MPJPE (mm): 433.59 -> 114.98Improved
use focal-length unification instead of learnable ray embedding (ablation)TAIHRI · Harmony4D-Egocentric (Upper)G-MPJPE (mm): 380.29 -> 93.83Improved
use focal-length unification instead of learnable ray embedding (ablation)TAIHRI · Harmony4D-Egocentric (L-Upper)G-MPJPE (mm): 400.09 -> 107.81Improved
add 2D keypoint reasoning before 3D prediction (ablation)TAIHRI · Harmony4D-Egocentric (Upper)G-MPJPE (mm): 126.67 -> 93.83Improved
add 2D keypoint reasoning before 3D prediction (ablation)TAIHRI · Harmony4D-Egocentric (Lower)G-MPJPE (mm): 138.39 -> 114.98Improved
add reinforcement finetuning (GRPO) after SFT (ablation)TAIHRI · Harmony4D-Egocentric (Upper)G-MPJPE (mm): 101.82 -> 93.83Improved
add reinforcement finetuning (GRPO) after SFT (ablation)TAIHRI · Harmony4D-Egocentric (R-Upper)G-MPJPE (mm): 110.79 -> 98.23Improved
use Huber+PCK reward instead of MSE reward in RFT (ablation)TAIHRI · Harmony4D-Egocentric (Upper)G-MPJPE (mm): 795.24 -> 93.83Improved
scale backbone from Qwen3-VL-2B to 4BTAIHRI · Harmony4D-Egocentric (L-Upper)G-MPJPE (mm): 119.86 -> 107.81Improved
scale backbone from Qwen3-VL-2B to 4BTAIHRI · EgoBody test sample (Upper)G-MPJPE (mm): 85.62 -> 75.77Improved
use TAIHRI instead of SAM 3D Body (3DB-H)close-range keypoint localization · Harmony4D-Egocentric (Upper)G-MPJPE (mm): 127.72 -> 93.83Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy